Skip to Content

Changes for page Automation

Last modified by Robert Schaub on 2025/12/24 20:34
From version 2.1
edited by Robert Schaub
on 2025/12/11 21:35
Change comment: Imported from XAR
To version 1.3
edited by Robert Schaub
on 2025/12/11 21:34
Change comment: Renamed back-links.

Summary

Details

Page properties
Content
... ... @@ -4,6 +4,7 @@
4 4  All automated outputs require human review before publication.
5 5  
6 6  This chapter defines:
7 +
7 7  * What must remain human-only
8 8  * What AI (AKEL) can draft
9 9  * What can be fully automated
... ... @@ -61,6 +61,7 @@
61 61  == POC (Low Automation) ==
62 62  
63 63  === Automated ===
65 +
64 64  * Claim normalization
65 65  * Light scenario templates
66 66  * Evidence metadata extraction
... ... @@ -67,6 +67,7 @@
67 67  * Simple verdict drafts (internal only)
68 68  
69 69  === Human ===
72 +
70 70  * All scenario definitions
71 71  * Evidence interpretation
72 72  * Verdict creation
... ... @@ -75,6 +75,7 @@
75 75  == Beta 0 (Medium Automation) ==
76 76  
77 77  === Automated ===
81 +
78 78  * Detailed scenario drafts
79 79  * Evidence reliability scoring
80 80  * Cross-scenario comparisons
... ... @@ -82,6 +82,7 @@
82 82  * Internal Truth Landscape drafts
83 83  
84 84  === Human ===
89 +
85 85  * Scenario approval
86 86  * Final verdict validation
87 87  
... ... @@ -88,6 +88,7 @@
88 88  == Release 1.0 (High Automation) ==
89 89  
90 90  === Automated ===
96 +
91 91  * Full scenario generation (definitions, assumptions, boundaries)
92 92  * Evidence relevance scoring and ranking
93 93  * Bayesian verdict scoring across scenario sets
... ... @@ -96,6 +96,7 @@
96 96  * AKEL-assisted federated synchronization
97 97  
98 98  === Human ===
105 +
99 99  * Final approval of all scenarios and verdicts
100 100  * Ethical decisions
101 101  * Oversight and conflict resolution
... ... @@ -105,15 +105,19 @@
105 105  = Automation Levels =
106 106  
107 107  == Level 0 — Human-Centric (POC) ==
115 +
108 108  AI is purely advisory, nothing auto-published.
109 109  
110 110  == Level 1 — Assisted (Beta 0) ==
119 +
111 111  AI drafts structures; humans approve each part.
112 112  
113 113  == Level 2 — Structured (Release 1.0) ==
123 +
114 114  AI produces near-complete drafts; humans refine.
115 115  
116 116  == Level 3 — Distributed Intelligence (Future) ==
127 +
117 117  Nodes exchange embeddings, contradiction alerts, and scenario templates.
118 118  Humans still approve everything.
119 119  
... ... @@ -122,6 +122,7 @@
122 122  = Automation Matrix =
123 123  
124 124  == Always Human ==
136 +
125 125  * Final verdict approval
126 126  * Scenario validity
127 127  * Ethical decisions
... ... @@ -128,6 +128,7 @@
128 128  * Dispute resolution
129 129  
130 130  == Mostly AI (Human Validation Needed) ==
143 +
131 131  * Claim normalization
132 132  * Clustering
133 133  * Evidence metadata
... ... @@ -136,6 +136,7 @@
136 136  * Contradiction detection
137 137  
138 138  == Mixed ==
152 +
139 139  * Definitions of ambiguous terms
140 140  * Boundary choices
141 141  * Assumption evaluation
... ... @@ -146,8 +146,8 @@
146 146  
147 147  = Diagram References =
148 148  
149 -{{include reference="FactHarbor.Specification.Diagrams.Automation Roadmap.WebHome"/}}
163 +{{include reference="FactHarbor.Archive.Diagrams v0\.8q.Automation Roadmap.WebHome"/}}
150 150  
151 -{{include reference="FactHarbor.Specification.Diagrams.Automation Level.WebHome"/}}
165 +{{include reference="FactHarbor.Archive.Diagrams v0\.8q.Automation Level.WebHome"/}}
152 152  
153 153  {{include reference="FactHarbor.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}